Results 1 - 10
of
34
Unsupervised Semantic Role Labelling
"... We present an unsupervised method for labelling the arguments of verbs with their semantic roles. Our bootstrapping algorithm makes initial unambiguous role assignments, and then iteratively updates the probability model on which future assignments are based. A novel aspect of our approach is the us ..."
Abstract
-
Cited by 77 (2 self)
- Add to MetaCart
We present an unsupervised method for labelling the arguments of verbs with their semantic roles. Our bootstrapping algorithm makes initial unambiguous role assignments, and then iteratively updates the probability model on which future assignments are based. A novel aspect of our approach is the use of verb, slot, and noun class information as the basis for backing off in our probability model. We achieve 50–65 % reduction in the error rate over an informed baseline, indicating the potential of our approach for a task that has heretofore relied on large amounts of manually generated training data.
J: Answering clinical questions with knowledgebased and statistical techniques
- Computational Linguistics
"... The combination of recent developments in question-answering research and the availability of unparalleled resources developed specifically for automatic semantic processing of text in the medical domain provides a unique opportunity to explore complex question answering in the domain of clinical me ..."
Abstract
-
Cited by 67 (10 self)
- Add to MetaCart
The combination of recent developments in question-answering research and the availability of unparalleled resources developed specifically for automatic semantic processing of text in the medical domain provides a unique opportunity to explore complex question answering in the domain of clinical medicine. This article presents a system designed to satisfy the information needs of physicians practicing evidence-based medicine. We have developed a series of knowledge extractors, which employ a combination of knowledge-based and statistical techniques, for automatically identifying clinically relevant aspects of MEDLINE abstracts. These extracted elements serve as the input to an algorithm that scores the relevance of citations with respect to structured representations of information needs, in accordance with the principles of evidencebased medicine. Starting with an initial list of citations retrieved by PubMed, our system can bring relevant abstracts into higher ranking positions, and from these abstracts generate responses that directly answer physicians ’ questions. We describe three separate evaluations: one focused on the accuracy of the knowledge extractors, one conceptualized as a document reranking task, and finally, an evaluation of answers by two physicians. Experiments on a collection of real-world clinical questions show that our approach significantly outperforms the already competitive PubMed baseline. 1.
Answer Extraction, Semantic Clustering, and Extractive Summarization for Clinical Question Answering
- Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL
, 2006
"... This paper presents a hybrid approach to question answering in the clinical domain that combines techniques from summarization and information retrieval. ..."
Abstract
-
Cited by 22 (3 self)
- Add to MetaCart
This paper presents a hybrid approach to question answering in the clinical domain that combines techniques from summarization and information retrieval.
Knowledge extraction for clinical question answering: preliminary results
- In Proceedings of the AAAI Workshop on Question Answering in Restricted Domains: 10 July 2005; Pittsburgh, PA. Edited by: Molla D, Vicedo JL
"... The combination of recent developments in question an-swering research and the unparalleled resources devel-oped specifically for automatic semantic processing of text in the medical domain provides a unique opportu-nity to explore complex question answering in the clin-ical domain. In this paper, w ..."
Abstract
-
Cited by 18 (7 self)
- Add to MetaCart
The combination of recent developments in question an-swering research and the unparalleled resources devel-oped specifically for automatic semantic processing of text in the medical domain provides a unique opportu-nity to explore complex question answering in the clin-ical domain. In this paper, we attempt to operationalize major aspects of evidence-based medicine in the form of knowledge extractors that serve as the fundamental building blocks of a clinical question answering sys-tem. Our evaluations demonstrate that domain-specific knowledge can be effectively leveraged to extract PICO frame elements from MEDLINE abstracts. Clinical in-formation systems in support of physicians ’ decision-making process have the potential to improve the qual-ity of patient care in real-world settings.
Analysis of polarity information in medical text
- In: Proceedings of the American Medical Informatics Association 2005 Annual Symposium
, 2005
"... Knowing the polarity of clinical outcomes is important in answering questions posed by clinicians in patient treatment. We treat analysis of this information as a classification problem. Natural language processing and machine learning techniques are applied to detect four possibilities in medical t ..."
Abstract
-
Cited by 15 (3 self)
- Add to MetaCart
(Show Context)
Knowing the polarity of clinical outcomes is important in answering questions posed by clinicians in patient treatment. We treat analysis of this information as a classification problem. Natural language processing and machine learning techniques are applied to detect four possibilities in medical text: no outcome, positive outcome, negative outcome, and neutral outcome. A supervised learning method is used to perform the classification at the sentence level. Five feature sets are constructed: UNIGRAMS, BIGRAMS, CHANGE PHRASES, NEGATIONS, and CATEGORIES. The performance of different combinations of feature sets is compared. The results show that generalization using the category information in the domain knowledge base Unified Medical Language System is effective in the task. The effect of context information is significant. Combining linguistic features and domain knowledge leads to the highest accuracy.
Title: An Evidence Perspective on Topical Relevance Types and Its Implications for Exploratory and Task-based Retrieval
"... 2002. She is interested in IR, specifically information retrieval interaction and knowledge organization from the user perspective, with a concentration in research methods. She is a research assistant on the five-year NSF-funded MALACH project and concentrates on studying the user needs and incorpo ..."
Abstract
-
Cited by 6 (3 self)
- Add to MetaCart
2002. She is interested in IR, specifically information retrieval interaction and knowledge organization from the user perspective, with a concentration in research methods. She is a research assistant on the five-year NSF-funded MALACH project and concentrates on studying the user needs and incorporating the user aspect into retrieval system development. For the MALACH speech retrieval test collection (which consists of the VHF (the Shoah Visual History Foundation) Holocaust survivor testimonies) she participated in designing the assessment interface, had a large role in defining the relevance types used, and managed the assessment process.
A Study of Structured Clinical Abstracts and the Semantic Classification of Sentences
"... This paper describes experiments in classifying sentences of medical abstracts into a number of semantic classes given by section headings in structured abstracts. Using conditional random fields, we obtain F-scores ranging from 0.72 to 0.97. By using a small set of sentences that appear under the P ..."
Abstract
-
Cited by 4 (0 self)
- Add to MetaCart
This paper describes experiments in classifying sentences of medical abstracts into a number of semantic classes given by section headings in structured abstracts. Using conditional random fields, we obtain F-scores ranging from 0.72 to 0.97. By using a small set of sentences that appear under the PAR-TICPANTS heading, we demonstrate that it is possible to recognize sentences that describe population characteristics of a study. We present a detailed study of the structure of abstracts of randomized clinical trials, and examine how sentences labeled under PAR-TICIPANTS could be used to summarize the population group. 1
Personalized Question Answering: A Use Case for Business Analysis
"... Abstract. In this paper, we introduce the Personalized Question Answering framework, which aims at addressing certain limitations of existing domain specific Question Answering systems. Current development efforts are ongoing to apply this framework to a use case within the domain of Business Analys ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
Abstract. In this paper, we introduce the Personalized Question Answering framework, which aims at addressing certain limitations of existing domain specific Question Answering systems. Current development efforts are ongoing to apply this framework to a use case within the domain of Business Analysis, highlighting the important role of domain specific semantics. Current research indicates that the inclusion of domain semantics helps to resolve the ambiguity problem and furthermore improves recall for retrieving relevant passages.
Situated Question Answering in the Clinical Domain: Selecting the Best Drug Treatment for Diseases
"... Unlike open-domain factoid questions, clinical information needs arise within the rich context of patient treatment. This environment establishes a number of constraints on the design of systems aimed at physicians in real-world settings. In this paper, we describe a clinical question answering syst ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
Unlike open-domain factoid questions, clinical information needs arise within the rich context of patient treatment. This environment establishes a number of constraints on the design of systems aimed at physicians in real-world settings. In this paper, we describe a clinical question answering system that focuses on a class of commonly-occurring questions: “What is the best drug treatment for X?”, where X can be any disease. To evaluate our system, we built a test collection consisting of thirty randomly-selected diseases from an existing secondary source. Both an automatic and a manual evaluation demonstrate that our system compares favorably to PubMed, the search system most commonly-used by physicians today. 1
A framework of a logic-based questionanswering system for the medical domain (loqas-med
- In Proceedings of the ACM Symposium on Applied Computing (SAC
, 2009
"... ABSTRACT Question-answering systems that provide precise answers to questions, by combining techniques for information retrieval, information extraction, and natural language processing, are seen as the next-generation search engines. Due to the growth and realworld impact of biomedical information ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
ABSTRACT Question-answering systems that provide precise answers to questions, by combining techniques for information retrieval, information extraction, and natural language processing, are seen as the next-generation search engines. Due to the growth and realworld impact of biomedical information, the need for questionanswering systems that can aid medical researchers and health care professionals in their information search is acutely felt. In order to provide users with accurate answers, such systems need to go beyond lexico-syntactic analysis to semantic analysis and processing of texts and knowledge resources. Moreover, questionanswering systems equipped with reasoning capabilities can derive more adequate answers by using inference. Research on question answering in the medical and health care domain is still in its inception stage. While several recent approaches to medical question answering have explored use of semantic knowledge, few approaches have exploited the utility of logic formalisms and of inference mechanisms. In this paper, we present a framework for a logic-based question-answering system for the medical domain, which uses Description Logic as the formalism for knowledge representation and reasoning. As a first step toward building the proposed system, we present semantic analysis and classification of medical questions.
